ContrAR (Multiple Frames) - Indoor Navigation: leaderboard

ContrAR (2026) tests whether vision-language models detect contradictory virtual content attacks in augmented reality, answering yes or no on real AR videos of which half carry an overlay that contradicts the physical scene, given the first, middle and last frames of each video. Detection accuracy in percent on the indoor navigation videos; higher is better.

Metric: Detection accuracy (%) for contradictory virtual content attacks in AR videos (54 indoor navigation videos; half the videos carry a contradiction, a balanced yes/no decision), first, middle and last frames given (multi-frame prompting); mean of three runs; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 11 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1GPT-4o88.89#751
2GPT-4.185.19#505
3Gemini 2.5 Pro83.33#276
4GPT-583.33#178
5Gemini 2.5 Flash75.93#463
6Grok 2 Vision74.07#1437
7Claude Sonnet 4.572.22#261
8Qwen 2.5 VL 7B Instruct72.22#1902
9Qwen 2.5 VL 72B Instruct72.22#841
10Grok 464.81#319
11Claude Haiku 4.553.7#583

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=contrar-multiple-frames-indoor-navigation · How It Works · Data refreshed daily, snapshot 2026-11-21.